CN-121973185-A - Virtual sampling based six-axis palletizing robot adaptation method, storage medium and system

CN121973185ACN 121973185 ACN121973185 ACN 121973185ACN-121973185-A

Abstract

The invention relates to the technical field of robot control, in particular to a six-axis palletizing robot adaptation method, a storage medium and a system based on virtual sampling. The method comprises the steps of obtaining parameter information and actual working environment information of a robot, determining a target working space of the robot through kinematic analysis, generating a pick-up point set and a placement point set of materials through virtual sampling based on the target working space, generating a path sample of the robot in a stacking process, carrying out track planning on the path sample, calculating and optimizing optimal motion parameters, carrying out robot action sequence scheduling optimization on the pick-up point set and the placement point set to obtain an optimal scheduling scheme, finally integrating the optimal motion parameters and the optimal scheduling scheme to generate a control program, and completing adaptation through verification and fine adjustment in the actual environment. According to the invention, the flexibility and the adaptability of the six-axis palletizing robot to various working scenes are improved through an automatic program generation mode.

Inventors

GUO DONG
CHENG MING
WANG WAN

Assignees

郭栋

Dates

Publication Date: 20260505
Application Date: 20251225

Claims (9)

1. The adaptation method of the six-axis palletizing robot based on the virtual sampling is characterized by comprising the following steps: acquiring parameter information and actual working environment information of a robot to be adapted; performing kinematic analysis on the robot based on the parameter information to obtain a working space boundary of the end effector of the robot; generating a pick-up point set and a placement point set of materials through virtual sampling based on the target working space, and generating a path sample set of the robot in the stacking process; Performing track planning on path samples in a path sample set, and calculating and optimizing optimal motion parameters, wherein the path samples comprise point-to-point paths, straight paths and circular paths; Constructing an objective function and a violation function to perform robot action sequence scheduling optimization on the pick-up point set and the placement point set to obtain an optimal scheduling scheme, wherein the objective function is used for maximizing the total number of stacked materials, minimizing the energy consumed by the stacked materials and maximizing the uniformity of filling of containers corresponding to all the stacked points; And integrating the optimal motion parameters and the optimal scheduling scheme to generate a control program, verifying the performance of the control program to generate a verification result, and performing fine adjustment according to the verification result to finish final adaptation.
2. The robot palletizer adapting method based on virtual sampling, as set forth in claim 1, wherein the kinematic analysis includes obtaining geometrical parameters and joint limit ranges of each link of the robot according to parameter information, establishing a robot base coordinate system, defining a local coordinate system for the links of the robot through the base coordinate system, obtaining DH parameters according to the local coordinate system, wherein the DH parameters are used for describing relative positions and postures between two adjacent links, establishing kinematic equations of the two adjacent local coordinate systems according to the DH parameters to obtain pose matrixes, and determining the working space boundary according to the pose matrixes and the limit ranges of the joints of the robot through a limit pacing angle method.
3. The robot palletizer adaptation method based on virtual sampling, which is characterized by comprising the steps of obtaining a key point set in the point-to-point path, optimizing and determining an optimal time interval sequence among key points by adopting a genetic algorithm, designing a first preset pose matrix of the robot at the key points, performing inverse solution operation on the first preset pose matrix to obtain a first preset joint angle of each joint of the robot at the key points, and performing spline curve interpolation for three times according to the first preset joint angle to generate joint angles, angular velocities and angular acceleration motion tracks forming a core motion instruction.
4. The robot palletizer adaptation method based on virtual sampling, as set forth in claim 1, is characterized in that the linear path specifically comprises the steps of obtaining coordinates of a start point and an end point of the linear path, inserting linear interpolation points on the linear path at equal time intervals by adopting a linear interpolation algorithm with acceleration and deceleration control, designing a second preset pose matrix of the robot at the linear interpolation points, performing inverse solution operation on the second preset pose matrix to obtain a second preset joint angle of a robot joint, and performing spline curve interpolation for three times according to the second preset joint angle to generate joint angles, angular velocities and angular acceleration motion tracks forming a core motion instruction.
5. The robot palletizer adapting method based on virtual sampling is characterized in that the arc path specifically comprises the steps of obtaining coordinates of a starting point, an ending point and a middle point of the arc path, determining and calculating the circle center and the radius of the arc path, establishing an arc coordinate system according to the plane where the circle center and the arc path are located, calculating arc interpolation points in the arc coordinate system according to the circle center and the radius by adopting an arc interpolation algorithm, converting the arc interpolation points into a base coordinate system from the arc coordinate system, designing a third preset pose matrix of the robot at the arc interpolation points, carrying out inverse solution operation on the third preset pose matrix to obtain a third preset joint angle of each joint of the robot, carrying out spline curve interpolation for three times according to the third preset joint angle, and generating a joint angle, an angular velocity and an angular acceleration motion track which form a core motion instruction.
6. The method for adapting the six-axis palletizing robot based on the virtual sampling as claimed in claim 3, wherein the optimization process of the genetic algorithm comprises constraint conditions, the constraint conditions comprise speed constraint, acceleration constraint and impact constraint, a cubic spline curve is obtained by constructing a cubic spline function according to the time interval sequence, angular speed, angular acceleration and angular jerk of each joint at any moment are obtained by analyzing the cubic spline curve, and the time interval sequence is reserved when the maximum angular speed, the maximum angular acceleration and the maximum angular jerk meet all constraint conditions.
7. The robot palletizing adaptive method based on the virtual sampling six axes is characterized in that the robot action sequence dispatching optimization specifically comprises the steps of randomly generating a first dispatching scheme set, randomly selecting an intermediate dispatching scheme based on the first dispatching scheme set, generating a first candidate dispatching scheme by combining the intermediate dispatching scheme with a current dispatching scheme, traversing the first dispatching scheme set to obtain a second dispatching scheme set, calculating the selection probability of the dispatching scheme in the second dispatching scheme set, taking the dispatching scheme with the highest selection probability as the intermediate dispatching scheme, generating a second candidate dispatching scheme by combining the intermediate dispatching scheme with the current dispatching scheme, carrying out preferred evaluation on the first candidate dispatching scheme and the second candidate dispatching scheme according to an objective function and a violation function, determining whether to update the dispatching scheme set or not based on an evaluation result, monitoring the dispatching scheme, replacing the dispatching scheme with a new random dispatching scheme when the dispatching scheme meets a preset stagnation condition, and re-executing the process until a preset algorithm termination condition is reached.
8. A computer readable storage medium having stored thereon a computer program, which when executed by a processor implements a virtual sampling based six axis palletizing robot adaptation method as claimed in any of claims 1-7.
9. Six pile up neatly robot adaptation systems based on virtual sampling, its characterized in that includes: The data acquisition module is used for acquiring parameter information and actual working environment information of the robot to be adapted; the kinematic analysis module is used for carrying out kinematic analysis on the robot based on the parameter information to obtain a working space boundary of the end effector of the robot; The system comprises a virtual sampling module, a target working space, a path sample collection module, a material stacking module and a material stacking module, wherein the virtual sampling module is used for determining a target working space according to actual working environment information and working space boundaries; The path planning module is used for carrying out path planning on the path samples in the path sample set and calculating optimal motion parameters; the scheduling optimization module is used for constructing an objective function and a violation function to perform robot action sequence scheduling optimization on the pick-up point set and the placement point set to obtain an optimal scheduling scheme; And the robot adaptation module integrates the optimal motion parameters and the optimal scheduling scheme to generate a control program, verifies the performance of the control program to generate a verification result, and performs fine adjustment according to the verification result to finish final adaptation.

Description

Virtual sampling based six-axis palletizing robot adaptation method, storage medium and system Technical Field The invention relates to the technical field of robot control, in particular to a six-axis palletizing robot adaptation method, a storage medium and a system based on virtual sampling. Background In the modern industrial field, an automation technology using an industrial robot as a core has become a key means for improving production efficiency and guaranteeing operation quality. Industrial robots offer their unique advantages, particularly in the areas of materials handling and stacking. Traditionally, programming and adapting such robots have relied on manual labor, and engineers have been required to write complex sequences of motion instructions to customize the robotic arms, gripping tools, control systems, etc. of the robot to ensure that the robot arm is compatible with a particular production process. However, as production scenarios become increasingly complex, new requirements are placed on the program control technology of existing robots. The prior art mainly solves the problem of how to make the manipulator accurately execute a predefined control program, but has some problems in coping with the situation that there are a plurality of dynamically changing initial positions and target positions in a working scene. In this multitasking scenario, the traditional offline programming method is struggled, because the preset program cannot autonomously decide and optimize the task execution order. The prior art has problems in how to automatically convert high-level job requirements into a complete control program comprising complex path planning and optimizing task scheduling. Therefore, a six-axis palletizing robot adapting method, a storage medium and a system based on virtual sampling are provided. Disclosure of Invention The invention aims to provide a six-axis palletizing robot adapting method, a storage medium and a system based on virtual sampling. Firstly, acquiring parameter information and actual working environment information of a robot to be adapted, performing kinematic analysis on the robot based on the parameter information to obtain a working space boundary of an end effector of the robot, then determining a target working space according to the actual working environment information and the working space boundary, generating a pick-up point set and a placement point set of materials through virtual sampling based on the target working space, generating a path sample set of the robot in a stacking process, performing track planning on the path sample in the path sample set, calculating and optimizing optimal motion parameters to ensure stable running and loss reduction of the robot, constructing a target function and an violation function to perform robot action sequence scheduling optimization on a plurality of stacking points, ensuring feasibility of a scheduling scheme while improving the optimizing efficiency to obtain an optimal scheduling scheme, finally integrating the optimal motion parameters and the optimal scheduling scheme to generate a control program, verifying performance of the control program to generate a verification result, and performing fine adjustment according to the verification result to finish final adaptation. According to the invention, the flexibility and the adaptability of the six-axis palletizing robot to various working scenes are improved through an automatic program generation mode. In order to achieve the above purpose, the present invention provides the following technical solutions: The adaptation method of the six-axis palletizing robot based on the virtual sampling comprises the following steps: acquiring parameter information and actual working environment information of a robot to be adapted; performing kinematic analysis on the robot based on the parameter information to obtain a working space boundary of the end effector of the robot; generating a pick-up point set and a placement point set of materials through virtual sampling based on the target working space, and generating a path sample set of the robot in the stacking process; Performing track planning on path samples in a path sample set, and calculating and optimizing optimal motion parameters, wherein the path samples comprise point-to-point paths, straight paths and circular paths; Constructing an objective function and a violation function to perform robot action sequence scheduling optimization on the pick-up point set and the placement point set to obtain an optimal scheduling scheme, wherein the objective function is used for maximizing the total number of stacked materials, minimizing the energy consumed by the stacked materials and maximizing the uniformity of filling of containers corresponding to all the stacked points; And integrating the optimal motion parameters and the optimal scheduling scheme to generate a control program, verifying the performance of the c